© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 11631
    Prev
    Next
    INDEX
    Explanations

    discussions around workplace dynamics and personal accountability in professional settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    berdayakan
    -1.03
     Anſ
    -1.01
    )";
    -0.97
    .)}
    -0.94
     déchir
    -0.94
     myſelf
    -0.92
     itſelf
    -0.92
     ་་
    -0.91
     Monfieur
    -0.90
     uș
    -0.89
    POSITIVE LOGITS
     Nowadays
    1.08
     nowadays
    1.06
     advices
    1.03
    Nowadays
    0.97
     Moreover
    0.88
    Apart
    0.84
    ´
    0.83
     Apart
    0.83
    Moreover
    0.83
     shrimps
    0.83
    Activations Density 8.744%

    No Known Activations